llvm-svn: 112104

expanding: e.g. <2 x float> -> <4 x float> instead of -> 2 floats.  This
affects two places in the code: handling cross block values and handling
function return and arguments.  Since vectors are already widened by 
legalizetypes, this gives us much better code and unblocks x86-64 abi
and SPU abi work.

For example, this (which is a silly example of a cross-block value):
define <4 x float> @test2(<4 x float> %A) nounwind {
 %B = shufflevector <4 x float> %A, <4 x float> undef, <2 x i32> <i32 0, i32 1>
 %C = fadd <2 x float> %B, %B
  br label %BB
BB:
 %D = fadd <2 x float> %C, %C
 %E = shufflevector <2 x float> %D, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
 ret <4 x float> %E
}

Now compiles into:

_test2:                                 ## @test2
## BB#0:
 addps %xmm0, %xmm0
 addps %xmm0, %xmm0
 ret

previously it compiled into:

_test2:                                 ## @test2
## BB#0:
 addps %xmm0, %xmm0
 pshufd $1, %xmm0, %xmm1
                                        ## kill: XMM0<def> XMM0<kill> XMM0<def>
 insertps $0, %xmm0, %xmm0
 insertps $16, %xmm1, %xmm0
 addps %xmm0, %xmm0
 ret

This implements rdar://8230384

llvm-svn: 112101

instructions, not when remapping modules.

llvm-svn: 112091

llvm-svn: 112090

llvm-svn: 112089

llvm-svn: 112086

llvm-svn: 112085

llvm-svn: 112084

llvm-svn: 112083

from MDValueList between each function, now that the bitcode
writer is reusing the index space for function-local metadata.

llvm-svn: 112082

llvm-svn: 112081

llvm-svn: 112080

llvm-svn: 112079

llvm-svn: 112076

When doing copy/paste/modify, it's apparently rather important to remember
the 'modify' bit...

llvm-svn: 112075

llvm-svn: 112073

DIGlobalVariable can be used to encode debug info for  globals that are directly folded into a constant by FE.

llvm-svn: 112072

llvm-svn: 112060

function-specific state.

llvm-svn: 112058

llvm-svn: 112056

llvm-svn: 112055

comparison that would overflow.
 - The other under/overflow cases can't actually happen because the immediates
   which would trigger them are legal (so we don't enter this code), but
   adjusted the style to make it clear the transform is always valid.

llvm-svn: 112053

llvm-svn: 112039

Mark _alloca call as clobberring EFLAGS, otherwise some DCE might remove
other flags-clobberring stuff (e.g. cmp instructions) occuring after
_alloca call.

llvm-svn: 112034

Fix some todos.  No functional change.

llvm-svn: 112031

llvm-svn: 112020

teach lowering to get target specific nodes for pshufd, emulating the same isel behavior for now, so we can pass all vector shuffle tests

llvm-svn: 112017

In the default address space, any GEP off of null results in a trap value if you try to load it.  Thus,
any load in the default address space that completes implies that the base value that it GEP'd from
was not null.

llvm-svn: 112015

for MDNodes, since this information is effectively implied by
the operands. This allow allows the code to avoid doing a
recursive is-it-really-function-local check in some cases.

llvm-svn: 111995

no functionality change.

llvm-svn: 111994

llvm-svn: 111993

functionality change.

llvm-svn: 111990

llvm-svn: 111982

llvm-svn: 111981

llvm-svn: 111974

to fix this in the port.

llvm-svn: 111973

llvm-svn: 111972

llvm-svn: 111971

access. rdar://8277890&7352504

llvm-svn: 111968

it is with other assemblers.

llvm-svn: 111967